Search Results for author: Jinho Lee

Found 22 papers, 7 papers with code

Pipe-BD: Pipelined Parallel Blockwise Distillation

1 code implementation29 Jan 2023 Hongsun Jang, Jaewon Jung, Jaeyong Song, Joonsang Yu, Youngsok Kim, Jinho Lee

However, this results in a high overhead of redundant teacher execution, low GPU utilization, and extra data loading.

SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators

1 code implementation25 Jan 2023 Mingi Yoo, Jaeyong Song, Jounghoo Lee, Namhyung Kim, Youngsok Kim, Jinho Lee

A GCN takes as input an arbitrarily structured graph and executes a series of layers which exploit the graph's structure to calculate their output features.

Feature Compression

Slice-and-Forge: Making Better Use of Caches for Graph Convolutional Network Accelerators

no code implementations24 Jan 2023 Mingi Yoo, Jaeyong Song, Hyeyoon Lee, Jounghoo Lee, Namhyung Kim, Youngsok Kim, Jinho Lee

Graph convolutional networks (GCNs) are becoming increasingly popular as they can process a wide variety of data formats that prior deep neural networks cannot easily support.

Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression

no code implementations24 Jan 2023 Jaeyong Song, Jinkyu Yim, Jaewon Jung, Hongsun Jang, Hyung-Jin Kim, Youngsok Kim, Jinho Lee

Compressing the communication is one way to mitigate the overhead by reducing the inter-node traffic volume; however, the existing compression techniques have critical limitations to be applied for NLP models with 3D parallelism in that 1) only the data parallelism traffic is targeted, and 2) the existing compression schemes already harm the model quality too much.

Enabling Hard Constraints in Differentiable Neural Network and Accelerator Co-Exploration

no code implementations23 Jan 2023 Deokki Hong, Kanghyun Choi, Hye Yoon Lee, Joonsang Yu, Noseong Park, Youngsok Kim, Jinho Lee

Co-exploration of an optimal neural architecture and its hardware accelerator is an approach of rising interest which addresses the computational cost problem, especially in low-profile systems.

Neural Architecture Search

ETF Portfolio Construction via Neural Network trained on Financial Statement Data

no code implementations4 Jul 2022 Jinho Lee, Sungwoo Park, Jungyu Ahn, Jonghun Kwak

Therefore, we use the data of individual stocks to train our neural networks to predict the future performance of individual stocks and use these predictions and the portfolio deposit file (PDF) to construct a portfolio of ETFs.


Shai-am: A Machine Learning Platform for Investment Strategies

no code implementations1 Jul 2022 Jonghun Kwak, Jungyu Ahn, Jinho Lee, Sungwoo Park

The finance industry has adopted machine learning (ML) as a form of quantitative research to support better investment decisions, yet there are several challenges often overlooked in practice.

BIG-bench Machine Learning

ConCoDE: Hard-constrained Differentiable Co-Exploration Method for Neural Architectures and Hardware Accelerators

no code implementations29 Sep 2021 Deokki Hong, Kanghyun Choi, Hey Yoon Lee, Joonsang Yu, Youngsok Kim, Noseong Park, Jinho Lee

To handle the hard constraint problem of differentiable co-exploration, we propose ConCoDE, which searches for hard-constrained solutions without compromising the global design objectives.

Neural Architecture Search

An Attention Module for Convolutional Neural Networks

no code implementations18 Aug 2021 Zhu Baozhou, Peter Hofstee, Jinho Lee, Zaid Al-Ars

To solve the two problems together, we initially propose an attention module for convolutional neural networks by developing an AW-convolution, where the shape of attention maps matches that of the weights rather than the activations.

Image Classification object-detection +1

GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent

no code implementations15 Feb 2021 Heesu Kim, Hanmin Park, Taehyun Kim, Kwanheum Cho, Eojin Lee, Soojung Ryu, Hyuk-Jae Lee, Kiyoung Choi, Jinho Lee

In this paper, we present GradPIM, a processing-in-memory architecture which accelerates parameter updates of deep neural networks training.

DANCE: Differentiable Accelerator/Network Co-Exploration

no code implementations14 Sep 2020 Kanghyun Choi, Deokki Hong, Hojae Yoon, Joonsang Yu, Youngsok Kim, Jinho Lee

In such circumstances, this work presents DANCE, a differentiable approach towards the co-exploration of the hardware accelerator and network architecture design.

Neural Architecture Search

SoFAr: Shortcut-based Fractal Architectures for Binary Convolutional Neural Networks

no code implementations11 Sep 2020 Zhu Baozhou, Peter Hofstee, Jinho Lee, Zaid Al-Ars

Inspired by the shortcuts and fractal architectures, we propose two Shortcut-based Fractal Architectures (SoFAr) specifically designed for BCNNs: 1. residual connection-based fractal architectures for binary ResNet, and 2. dense connection-based fractal architectures for binary DenseNet.


MAPS: Multi-agent Reinforcement Learning-based Portfolio Management System

no code implementations10 Jul 2020 Jinho Lee, Raehyun Kim, Seok-Won Yi, Jaewoo Kang

Generating an investment strategy using advanced deep learning methods in stock markets has recently been a topic of interest.

Management Multi-agent Reinforcement Learning +2

SimEx: Express Prediction of Inter-dataset Similarity by a Fleet of Autoencoders

no code implementations14 Jan 2020 Inseok Hwang, Jinho Lee, Frank Liu, Minsik Cho

Our intuition is that, the more similarity exists between the unknown data samples and the part of known data that an autoencoder was trained with, the better chances there could be that this autoencoder makes use of its trained knowledge, reconstructing output samples closer to the originals.

Data Augmentation

MUTE: Data-Similarity Driven Multi-hot Target Encoding for Neural Network Design

no code implementations15 Oct 2019 Mayoore S. Jaiswal, Bumboo Kang, Jinho Lee, Minsik Cho

Target encoding is an effective technique to deliver better performance for conventional machine learning methods, and recently, for deep neural networks as well.

General Classification Image Classification

Global Stock Market Prediction Based on Stock Chart Images Using Deep Q-Network

1 code implementation28 Feb 2019 Jinho Lee, Raehyun Kim, Yookyung Koh, Jaewoo Kang

Moreover, the results show that future stock prices can be predicted even if the training and testing procedures are done in different countries.

Stock Market Prediction

Globally Optimal Object Tracking with Fully Convolutional Networks

no code implementations25 Dec 2016 Jinho Lee, Brian Kenji Iwana, Shouta Ide, Seiichi Uchida

Thus, we propose a new and robust tracking method using a Fully Convolutional Network (FCN) to obtain an object probability map and Dynamic Programming (DP) to seek the globally optimal path through all frames of video.

Object Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.